Decentralized Optimal Equilibrium Learning Over Dynamic Networks

The paper introduces a decentralized learning framework for finding socially optimal equilibria in finite normal-form games played over dynamic communication networks. Agents only observe their own payoffs, lack prior knowledge of the game, and communicate with time-varying neighbors using low-bandwidth, time-stamped tables instead of raw actions or payoff data. The proposed dynamics combine randomized semantic signals, table fusion, and temporal majority reconstruction to achieve finite-time logarithmic regret guarantees for optimal equilibrium selection under utilitarian and proportional-fair social welfare objectives, as demonstrated by simulations.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

• agents